A question about LLaMA-2-7B and Mistral models only provide Dense-only (0%) quantized models #56
Description
Hello, I have a question that I hope can be answered.
Why do LLaMA-2-7B and Mistral models only provide Dense-only (0%) quantized models, but not 0.05% Sparsity and 0.45% sparsity quantized models?
Is it because the quantization effect is not good for these two models?
thanks